Skip to main content
ACE StudioMediumStandard

ACE-Step

ACE-Step open music foundation model via Replicate. Generates up to 4 minutes of music with vocals from style tags and structured lyrics, with full control over steps, scheduler and guidance. Billed per second of requested duration.

16 credits
per 60s at 60 steps โ€” (2.72 + 0.21 ร— seconds) ร— steps/60, measured
Open-source music model with vocals
Up to 240 seconds per generation
Style tags instead of prose prompts
Full control of steps, scheduler and guidance
Measured pricing: 16 credits per minute at default steps

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "lucataco/ace-step",
  "input": {
    "tags": "k-pop, electro-pop, company jingle, synth brass, punchy drums, 128 BPM, energetic, playful, female vocals, korean",
    "lyrics": "[verse]\n์•„์นจ๋ถ€ํ„ฐ AI, ์ปคํ”ผ๋ณด๋‹ค ์ง„ํ•ด\n์ฝ”๋”ฉํ•˜๋‹ค ๋ณด๋‹ˆ ๋ฒŒ์จ ์ƒˆ๋ฒฝ ๋‘ ์‹œ๋„ค!\n์•ˆ ๋˜๋Š” ๊ฑด ์—†์–ด, ์ผ๋‹จ ๋งŒ๋“ค์–ด ๋ด\n์ƒ์ƒ์ด ํ˜„์‹ค ๋˜๋Š” ๋งˆ๋ฒ• ๊ฐ™์€ ํšŒ์‚ฌ!\n\n[chorus]\n์ฝ”์–ด! ๋‹ท! ํˆฌ๋ฐ์ด!\n์˜ค๋Š˜์˜ ์ƒ์ƒ์ด ๋‚ด์ผ์˜ ๊ธฐ์ˆ ๋กœ!\n์ฝ”์–ด! ๋‹ท! ํˆฌ๋ฐ์ด!\nAI๋„ ๋†€๋ผ๋Š” ์šฐ๋ฆฌ์˜ ์•„์ด๋””์–ด!\n\n[outro]\n๋š๋”ฑ๋š๋”ฑ ๋งŒ๋“ค๊ณ , ๋ฐ˜์ง๋ฐ˜์ง ๋น›๋‚ด๊ณ !\n๊ธฐ์ˆ ์„ ๋„˜์–ด ๊ฒฝํ—˜์œผ๋กœ!\n์ฝ”์–ด๋‹ทํˆฌ๋ฐ์ด, Hey!",
    "duration": 60
  }
}'

Parameters

ParameterTypeRequiredDefaultDescription
tagsstringYes-Comma-separated style tags, e.g. 'synth-pop, electronic, 128 BPM, energetic'
lyricsstringNo-Lyrics with [verse], [chorus], [bridge] sections. Use [instrumental] or [inst] for instrumental music
durationnumberNo60Duration of the generated audio in seconds (1-240). Billed per second
number_of_stepsintegerNo60Number of inference steps (10-200)
seedintegerNo-1Random seed. -1 randomizes
schedulerstringNoeulerScheduler type
eulerheun
guidance_typestringNoapgGuidance type for CFG
apgcfgcfg_star
guidance_scalenumberNo15Overall guidance scale (0-30)
granularity_scalenumberNo10Omega scale for APG guidance (-100 to 100)
guidance_intervalnumberNo0.5Guidance interval (0-1)
guidance_interval_decaynumberNo0Guidance interval decay (0-1)
min_guidance_scalenumberNo3Minimum guidance scale (0-100)
tag_guidance_scalenumberNo0Guidance scale for tags (0-10)
lyric_guidance_scalenumberNo0Guidance scale for lyrics (0-10)

Common Parameters

Common parameters used when calling POST /v1/predictions.

ParameterTypeRequiredDefaultDescription
modelstringYes-Model identifier
inputobjectYes-Object containing the model-specific parameters from the table above
output_folderstringNo-Folder path for output files (max 256 chars, '..' not allowed)
webhook_urlstringNo-Webhook URL to call on completion
is_publicbooleanNofalseIf true, output files are also available via permanent public URLs

Examples

Core.Today company song

The same Korean company-song lyrics given to every music model โ€” compare how each one sings them

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "lucataco/ace-step",
  "input": {
    "tags": "k-pop, electro-pop, company jingle, synth brass, punchy drums, 128 BPM, energetic, playful, female vocals, korean",
    "lyrics": "[verse]\n์•„์นจ๋ถ€ํ„ฐ AI, ์ปคํ”ผ๋ณด๋‹ค ์ง„ํ•ด\n์ฝ”๋”ฉํ•˜๋‹ค ๋ณด๋‹ˆ ๋ฒŒ์จ ์ƒˆ๋ฒฝ ๋‘ ์‹œ๋„ค!\n์•ˆ ๋˜๋Š” ๊ฑด ์—†์–ด, ์ผ๋‹จ ๋งŒ๋“ค์–ด ๋ด\n์ƒ์ƒ์ด ํ˜„์‹ค ๋˜๋Š” ๋งˆ๋ฒ• ๊ฐ™์€ ํšŒ์‚ฌ!\n\n[chorus]\n์ฝ”์–ด! ๋‹ท! ํˆฌ๋ฐ์ด!\n์˜ค๋Š˜์˜ ์ƒ์ƒ์ด ๋‚ด์ผ์˜ ๊ธฐ์ˆ ๋กœ!\n์ฝ”์–ด! ๋‹ท! ํˆฌ๋ฐ์ด!\nAI๋„ ๋†€๋ผ๋Š” ์šฐ๋ฆฌ์˜ ์•„์ด๋””์–ด!\n\n[outro]\n๋š๋”ฑ๋š๋”ฑ ๋งŒ๋“ค๊ณ , ๋ฐ˜์ง๋ฐ˜์ง ๋น›๋‚ด๊ณ !\n๊ธฐ์ˆ ์„ ๋„˜์–ด ๊ฒฝํ—˜์œผ๋กœ!\n์ฝ”์–ด๋‹ทํˆฌ๋ฐ์ด, Hey!",
    "duration": 60
  }
}'

Synth-pop with lyrics

Tag prompt plus sectioned lyrics, 60 seconds

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "lucataco/ace-step",
  "input": {
    "tags": "synth-pop, electronic, pop, synthesizer, drums, bass, piano, 128 BPM, energetic, uplifting, modern",
    "lyrics": "[verse]\nWoke up in a city that's always alive\nNeon lights they shimmer they thrive\n\n[chorus]\nOh we ride the night\nelectric hearts alight",
    "duration": 60
  }
}'

Tips & Best Practices

1Use tags, not sentences: genre, instruments, BPM, mood separated by commas
2Write [inst] as the lyrics for an instrumental track
3Billing follows duration and number_of_steps โ€” 240 s at 60 steps is about 54 credits, 200 steps triples it
4Leave the guidance parameters at their defaults unless you are experimenting

Use Cases

Cheap full-length song drafts
Experiments with guidance and schedulers
Instrumental tracks via [inst] lyrics